Commit Graph
28 Commits
Author SHA1 Message Date
somew1nd bb16991f2c feat: harden video analysis and runtime resilience 2026-08-25 20:58:25 -07:00
somew1nd 5ada543a09 docs: standardize image embedding widths to 100% and streamline emoji usage 2026-08-25 17:09:10 -07:00
somew1nd ef5748c8f1 docs: remove live demo caption under demo gif in README 2026-08-25 17:04:08 -07:00
somew1nd c2ff9651cc docs: remove outer canvas padding from leaderboard to match architecture diagram 2026-08-25 17:02:50 -07:00
somew1nd 4f8a83ebd3 docs: use new asset path to bust GitHub camo image cache for leaderboard 2026-08-25 17:00:38 -07:00
somew1nd 4bf1160e5b docs: refresh AndroidWorld benchmark visual and streamline architecture overview in README 2026-08-25 16:58:44 -07:00
somew1nd ea3708a98f feat: implement robust multi-tier text input architecture and ADB diagnostics
- Android Text Input & IME Normalization:
  - Implement progressive 3-tier input architecture in AndroidAdbDriver and AndroidDeviceController:
    - Tier 1 (Primary): Zero-dependency clipboard injection + KEYCODE_PASTE (immune to IME Pinyin interception, full Unicode/Emoji support, preserves multiline formatting).
    - Tier 2 (Broadcast): Base64 broadcast injection when ADBKeyboard is active.
    - Tier 3 (Fallback): Native ADB physical keyevent fallback.
  - Add literal newline normalization (\r\n, \n, \r) to prevent JSON escape string corruption (e.g. '10086\n' -> '10086、n').
  - Add set_clipboard method to UIAutomatorClient without auxiliary APK requirements.

- Diagnostics & System Probes:
  - Add adb_keys diagnostics probe for ADB key auth checks.
  - Integrate diagnostics into CLI doctor command.

- Admin Console & Showcase UI:
  - Improve model service and system router in admin console.
  - Enhance workspace stream view and session state in showcase UI.
2026-08-24 16:48:45 -07:00
somew1nd 42b8988661 feat: add global device queue and readiness tracking 2026-08-24 14:34:17 -07:00
somew1nd a62ac4aef1 fix: finalize recordings before automatic replay 2026-08-23 13:06:19 -07:00
somew1nd 474e56ef8e feat: support orientation-aware recording and device wakefulness
Roll scrcpy recordings by device rotation and duration, and publish timeline manifests for playback and analysis.

Add seamless segmented playback in the showcase UI and configurable stay-awake strategies for Android automation.
2026-08-22 19:45:02 -07:00
somew1nd 160f43a74a docs: refresh banner and update tagline to 'Let AI assistants and test suites use real phones like a human' 2026-08-21 12:24:56 -07:00
somew1nd 71e5bba551 runtime: harden LLM retry handling and operator workflows 2026-08-21 00:34:44 -07:00
somew1nd 0f5fb1d32c Improve task resilience and LLM retry visibility
Persist and publish recoverable provider retries so temporary 503 and throttling events remain visible in live and historical task streams.

Aggregate repeated retries into an expandable action card, preserve terminal pause recovery, harden Windows worker isolation and output forwarding, and retain reliable Android hierarchy fallbacks with regression coverage.
2026-08-20 00:37:53 -07:00
somew1nd c1a4b49a21 feat(mcp): enhance multi-platform notification resilience and reactive wakeups
- AgentApiNotifier: Sort candidate process sessions by creation time descending to prioritize the latest active IDE session over stale PIDs. Implement automatic retry across candidate address/token pairs and persist working credentials to shared environment files (~/.gemini/jetski/.jetski_env and ~/.artemis/.artemis_env).
- DesktopNotifier: Enable native OS desktop toast notifications by default on macOS, Linux, and Windows unless explicitly disabled or running in CI. Ensure MCP installer sets ARTEMIS_DESKTOP_NOTIFY=true in generated IDE configurations.
- ScriptNotifier: Add universal command hook adapter (ARTEMIS_NOTIFY_CMD / MCP_NOTIFY_COMMAND) for custom IDE and CLI integration.
- Fault Isolation: Wrap CompositeNotifier and global notify entrypoint in strict try-except blocks to guarantee zero-crash execution even if any individual notifier fails.
- Tests & Docs: Add unit tests for session recovery, fault tolerance, script hook execution, and document multi-platform notification architecture in README.
2026-08-19 11:34:46 -07:00
somew1nd 4927c4f0b9 Stabilize task execution and UI lifecycle 2026-08-19 00:47:45 -07:00
somew1nd c78c201e94 Fix setup UI and improve CLI workflows 2026-08-18 22:35:05 -07:00
somew1nd ec5010220b feat(mcp): implement double-insurance global-only MCP and testing rules installation
- Install MCP configs and Artemis mobile testing rules strictly into user home directories (~), avoiding project workspace pollution
- Add double-insurance rules synchronization injecting into both primary global instruction files (e.g. ~/.gemini/GEMINI.md, ~/.claude/CLAUDE.md, ~/.cursorrules, ~/.codeium/windsurf/memories/global_rules.md) and modular rules/ directories
- Support JSONC parsing (comments and trailing commas) and automatic .bak backups when merging existing IDE configuration files
- Update README and Quick Start documentation to clarify automatic global MCP & rule mounting across all major AI IDEs
2026-08-18 18:40:38 -07:00
somew1nd 9e5aee85c8 fix(mcp): auto-register tools on startup and support cross-platform setup for all major AI IDEs
- Fix missing mcp_server.tools import on server initialization so mobile_run_task, mobile_manage_task, mobile_get_device_state, and mobile_inspect_trace are automatically registered.

- Inject PYTHONPATH in generated and installed MCP configurations to guarantee Python module resolution across Windows, macOS, and Linux regardless of IDE CWD.

- Expand artemis mcp --install and --generate-config to support VS Code, Cline, Roo Code, Claude Code CLI (~/.claude.json), Cursor, Windsurf, Antigravity, and OpenClaw.

- Enhance config file merging with robust exception handling and fallback initialization.
2026-08-18 17:49:47 -07:00
somew1nd fc6ddad655 feat(ui): ensure cross-platform one-click setup and default Showcase UI routing
- Add explicit root route (/) in server.py to guarantee Showcase UI is served by default, routing /admin to the Admin Debug Console
- Enhance dynamic Angular dist detection across multiple standard output paths
- Add automated Node.js/npm detection and installation fallbacks to start scripts and installers across macOS, Linux, and Windows
- Automatically build Showcase UI when launching via start.sh, start.bat/start.ps1, or artemis ui if frontend artifacts are missing
- Add Node.js / npm and Showcase UI status inspection rows to artemis doctor
- Support artemis mcp --install for one-click IDE integration and add make build-ui target
2026-08-18 17:22:49 -07:00
somew1nd 6fa4768893 docs: refine Chinese banner tagline to Artemis and refresh cache 2026-08-18 15:37:21 -07:00
somew1nd 1899c68bb8 docs: elevate banner tagline to Autonomous Assistant Platform and update renders 2026-08-18 15:33:28 -07:00
somew1nd 46e1e8b935 docs: update banner tagline to Android Phone and add native Chinese banner 2026-08-18 15:30:18 -07:00
somew1nd 62cb3d8e53 docs: emphasize testing real devices in README subtitles 2026-08-18 15:22:21 -07:00
somew1nd 1d005d08a9 docs: broaden UI testing terminology to general test automation across README 2026-08-18 15:20:50 -07:00
somew1nd 19c74717ab docs: add cache buster to banner image URLs to bypass GitHub CDN caching 2026-08-18 15:18:34 -07:00
somew1nd a306258d26 docs: add Antigravity x ARTEMIS autonomous testing workflow showcase and update banner 2026-08-18 15:13:39 -07:00
somew1nd 9a5aaf99b7 feat: introduce MCP server, cross-platform runtime, and Showcase UI reorganization
- Showcase UI Reorganization:
  * Move web UI dashboard from root directory into apps/showcase_ui/ for cleaner project structure
  * Add 'artemis ui' CLI command (artemis/interfaces/cli/commands/ui.py) and launcher scripts for the interactive showcase console
- Standalone MCP Server & Notifiers (mcp_server/):
  * Implement dedicated MCP server package with mobile automation tools (device_state, inspect_trace, task_manager, task_runner)
  * Add multi-channel notifiers (AgentAPI, Desktop notifications, Webhooks, File output, and Composite routing)
  * Introduce background task runner and trace store for autonomous mobile execution monitoring
- Cross-Platform Runtime & Toolchain Support:
  * Add artemis/platform/ with OS-specific implementations for Linux, macOS (Darwin), and Windows
  * Add artemis/runtime/supervisor.py for resilient process and agent runtime supervision
  * Add artemis/toolchain/ with dependency resolution and SDK descriptors
  * Add cross-platform launcher scripts (start.sh, start.bat) and installer scripts (scripts/install_deps.*)
- Core Enhancements & Diagnostics:
  * Enhance coordinate normalization, OCR API fallback, and perception pipeline
  * Add credential validation (credentials_validator.py) and system diagnostics
  * Update bilingual documentation (README.md, README_CN.md) and architecture diagrams
- Test Suite Expansion:
  * Add integration tests for cloud gateway, remote ADB, and Artemis login
  * Add unit tests covering core diagnostics, platform detection, toolchain, credentials validator, optional OCR, and MCP tools
2026-08-18 13:59:27 -07:00
somew1nd 206a9ce921 feat: initial release of ARTEMIS Android Agent & Automation Platform
ARTEMIS is an autonomous multimodal Android agent and mobile UI automation
platform engineered for physical devices and emulators. It combines state-of-the-art
multimodal Vision-Language Models (VLMs) with hierarchical closed-loop planning,
resilient self-healing, and deep Android subsystem integration.

Key Features & Architectural Highlights:
- Dual-Engine Orchestration:
  * Pro Engine: Multi-agent closed-loop (Planner -> Operator -> Validator/Failure Analyzer -> Summarizer) powered by LangGraph.
  * Flash Engine: Ultra-fast reactive loop for deterministic, low-latency UI execution (<35 steps).
- Multimodal Perception & Grounding:
  * Hybrid visual screenshot grounding, real-time OCR extraction, and XML accessibility hierarchy parsing.
  * Dynamic-First, Coordinate-Fallback locating strategy for maximum resilience against UI drift.
- Autonomous Self-Healing & Diagnostics:
  * Failure analyzer and safety net for popup dismissal, crash recovery, and auto-retry.
  * Diagnostic sub-agents for log analysis, video recording inspection, and object detection.
- Unified CLI & Python SDK:
  * Rich CLI with commands: init, doctor, run, trace, batch, bench, server, and mcp.
  * Fluent Python SDK with Pydantic structured output models and package locking.
- Multi-Provider LLM Architecture:
  * Support for Google Gemini, OpenAI, Anthropic Claude, Vertex AI, OpenRouter, xAI Grok, and local endpoints (Ollama/vLLM).
  * Centralized configuration in config/artemis.jsonc.
- Native MCP & Observability:
  * Model Context Protocol (MCP) server endpoints for AI IDEs.
  * Full trace recording with before/after screenshots, action overlays, and execution replays.

Change-Id: I430b93ee2b76b54cc5a3c6eeccd15d2cf29830a1
2026-08-13 11:46:47 -07:00